Carnegie Mellon University


March 01, 2019

CyLab team studies user behavior to detect malicious websites

In an article for Security Magazine, ECE Ph.D. student Mahmood Sharif spoke about a CyLab research study to predict and detect malicious websites before users are exposed to them. The team analyzed the relationship between user behavior and malicious websites with data covering three months of web traffic from 20,000 users in 2017. They found that 11 percent of users were exposed to malicious websites, and that users who visited pages with more ads and browsed more at night were more exposed. “Most traditional security defenses are reactive, and warn users only after or at the time they’ve visited a malicious website,” said Sharif. “We wanted to figure out: are there hints about a user’s behavior that could tell us when something bad is going to happen before it happens?” Read the article here.